xen: add more Xen dom0 support

@@ -793,7 +793,7 @@
 
 	ret = 0;
 
-	switch(msr) {
+	switch (msr) {
 #ifdef CONFIG_X86_64
 		unsigned which;
 		u64 base;

@@ -1453,7 +1453,7 @@
 
 	ident_pte = 0;
 	pfn = 0;
-	for(pmdidx = 0; pmdidx < PTRS_PER_PMD && pfn < max_pfn; pmdidx++) {
+	for (pmdidx = 0; pmdidx < PTRS_PER_PMD && pfn < max_pfn; pmdidx++) {
 		pte_t *pte_page;
 
 		/* Reuse or allocate a page of ptes */

@@ -1471,7 +1471,7 @@
 		}
 
 		/* Install mappings */
-		for(pteidx = 0; pteidx < PTRS_PER_PTE; pteidx++, pfn++) {
+		for (pteidx = 0; pteidx < PTRS_PER_PTE; pteidx++, pfn++) {
 			pte_t pte;
 
 			if (pfn > max_pfn_mapped)

@@ -1485,7 +1485,7 @@
 		}
 	}
 
-	for(pteidx = 0; pteidx < ident_pte; pteidx += PTRS_PER_PTE)
+	for (pteidx = 0; pteidx < ident_pte; pteidx += PTRS_PER_PTE)
 		set_page_prot(&level1_ident_pgt[pteidx], PAGE_KERNEL_RO);
 
 	set_page_prot(pmd, PAGE_KERNEL_RO);

@@ -1499,7 +1499,7 @@
 
 	/* All levels are converted the same way, so just treat them
 	   as ptes. */
-	for(i = 0; i < PTRS_PER_PTE; i++)
+	for (i = 0; i < PTRS_PER_PTE; i++)
 		pte[i] = xen_make_pte(pte[i].pte);
 }
 

@@ -1514,7 +1514,8 @@
  * of the physical mapping once some sort of allocator has been set
  * up.
  */
-static __init pgd_t *xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn)
+static __init pgd_t *xen_setup_kernel_pagetable(pgd_t *pgd,
+						unsigned long max_pfn)
 {
 	pud_t *l3;
 	pmd_t *l2;

@@ -1577,7 +1578,8 @@
 #else	/* !CONFIG_X86_64 */
 static pmd_t level2_kernel_pgt[PTRS_PER_PMD] __page_aligned_bss;
 
-static __init pgd_t *xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn)
+static __init pgd_t *xen_setup_kernel_pagetable(pgd_t *pgd,
+						unsigned long max_pfn)
 {
 	pmd_t *kernel_pmd;
 

@@ -154,13 +154,13 @@
 {
 	unsigned pfn, idx;
 
-	for(pfn = 0; pfn < MAX_DOMAIN_PAGES; pfn += P2M_ENTRIES_PER_PAGE) {
+	for (pfn = 0; pfn < MAX_DOMAIN_PAGES; pfn += P2M_ENTRIES_PER_PAGE) {
 		unsigned topidx = p2m_top_index(pfn);
 
 		p2m_top_mfn[topidx] = virt_to_mfn(p2m_top[topidx]);
 	}
 
-	for(idx = 0; idx < ARRAY_SIZE(p2m_top_mfn_list); idx++) {
+	for (idx = 0; idx < ARRAY_SIZE(p2m_top_mfn_list); idx++) {
 		unsigned topidx = idx * P2M_ENTRIES_PER_PAGE;
 		p2m_top_mfn_list[idx] = virt_to_mfn(&p2m_top_mfn[topidx]);
 	}

@@ -179,7 +179,7 @@
 	unsigned long max_pfn = min(MAX_DOMAIN_PAGES, xen_start_info->nr_pages);
 	unsigned pfn;
 
-	for(pfn = 0; pfn < max_pfn; pfn += P2M_ENTRIES_PER_PAGE) {
+	for (pfn = 0; pfn < max_pfn; pfn += P2M_ENTRIES_PER_PAGE) {
 		unsigned topidx = p2m_top_index(pfn);
 
 		p2m_top[topidx] = &mfn_list[pfn];

@@ -207,7 +207,7 @@
 	p = (void *)__get_free_page(GFP_KERNEL | __GFP_NOFAIL);
 	BUG_ON(p == NULL);
 
-	for(i = 0; i < P2M_ENTRIES_PER_PAGE; i++)
+	for (i = 0; i < P2M_ENTRIES_PER_PAGE; i++)
 		p[i] = INVALID_P2M_ENTRY;
 
 	if (cmpxchg(pp, p2m_missing, p) != p2m_missing)

@@ -407,7 +407,8 @@
 		preempt_enable();
 }
 
-pte_t xen_ptep_modify_prot_start(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
+pte_t xen_ptep_modify_prot_start(struct mm_struct *mm,
+				 unsigned long addr, pte_t *ptep)
 {
 	/* Just return the pte as-is.  We preserve the bits on commit */
 	return *ptep;

@@ -871,7 +872,8 @@
 
 		if (user_pgd) {
 			xen_pin_page(mm, virt_to_page(user_pgd), PT_PGD);
-			xen_do_pin(MMUEXT_PIN_L4_TABLE, PFN_DOWN(__pa(user_pgd)));
+			xen_do_pin(MMUEXT_PIN_L4_TABLE,
+				   PFN_DOWN(__pa(user_pgd)));
 		}
 	}
 #else /* CONFIG_X86_32 */

@@ -986,7 +988,8 @@
 		pgd_t *user_pgd = xen_get_user_pgd(pgd);
 
 		if (user_pgd) {
-			xen_do_pin(MMUEXT_UNPIN_TABLE, PFN_DOWN(__pa(user_pgd)));
+			xen_do_pin(MMUEXT_UNPIN_TABLE,
+				   PFN_DOWN(__pa(user_pgd)));
 			xen_unpin_page(mm, virt_to_page(user_pgd), PT_PGD);
 		}
 	}

@@ -154,7 +154,7 @@
 			       ret, smp_processor_id());
 			dump_stack();
 			for (i = 0; i < b->mcidx; i++) {
-				printk("  call %2d/%d: op=%lu arg=[%lx] result=%ld\n",
+				printk(KERN_DEBUG "  call %2d/%d: op=%lu arg=[%lx] result=%ld\n",
 				       i+1, b->mcidx,
 				       b->debug[i].op,
 				       b->debug[i].args[0],

@@ -28,6 +28,9 @@
 /* These are code, but not functions.  Defined in entry.S */
 extern const char xen_hypervisor_callback[];
 extern const char xen_failsafe_callback[];
+extern void xen_sysenter_target(void);
+extern void xen_syscall_target(void);
+extern void xen_syscall32_target(void);
 
 
 /**

@@ -110,7 +113,6 @@
 
 void __cpuinit xen_enable_sysenter(void)
 {
-	extern void xen_sysenter_target(void);
 	int ret;
 	unsigned sysenter_feature;
 

@@ -132,8 +134,6 @@
 {
 #ifdef CONFIG_X86_64
 	int ret;
-	extern void xen_syscall_target(void);
-	extern void xen_syscall32_target(void);
 
 	ret = register_callback(CALLBACKTYPE_syscall, xen_syscall_target);
 	if (ret != 0) {

@@ -160,7 +160,8 @@
 	HYPERVISOR_vm_assist(VMASST_CMD_enable, VMASST_TYPE_writable_pagetables);
 
 	if (!xen_feature(XENFEAT_auto_translated_physmap))
-		HYPERVISOR_vm_assist(VMASST_CMD_enable, VMASST_TYPE_pae_extended_cr3);
+		HYPERVISOR_vm_assist(VMASST_CMD_enable,
+				     VMASST_TYPE_pae_extended_cr3);
 
 	if (register_callback(CALLBACKTYPE_event, xen_hypervisor_callback) ||
 	    register_callback(CALLBACKTYPE_failsafe, xen_failsafe_callback))

@@ -8,8 +8,6 @@
 extern int iommu_detected;
 extern int dmar_disabled;
 
-extern unsigned long iommu_nr_pages(unsigned long addr, unsigned long len);
-
 /* 10 seconds */
 #define DMAR_OPERATION_TIMEOUT ((cycles_t) tsc_khz*10*1000)
 

@@ -125,13 +125,6 @@
 	pci_swiotlb_init();
 }
 
-unsigned long iommu_nr_pages(unsigned long addr, unsigned long len)
-{
-	unsigned long size = roundup((addr & ~PAGE_MASK) + len, PAGE_SIZE);
-
-	return size >> PAGE_SHIFT;
-}
-EXPORT_SYMBOL(iommu_nr_pages);
 #endif
 
 void *dma_generic_alloc_coherent(struct device *dev, size_t size,

@@ -10,6 +10,9 @@
 extern void
 swiotlb_init(void);
 
+extern void *swiotlb_alloc_boot(size_t bytes, unsigned long nslabs);
+extern void *swiotlb_alloc(unsigned order, unsigned long nslabs);
+
 extern void
 *swiotlb_alloc_coherent(struct device *hwdev, size_t size,
 			dma_addr_t *dma_handle, gfp_t flags);

@@ -21,6 +21,7 @@
 #include <linux/mm.h>
 #include <linux/module.h>
 #include <linux/spinlock.h>
+#include <linux/swiotlb.h>
 #include <linux/string.h>
 #include <linux/types.h>
 #include <linux/ctype.h>

@@ -126,6 +127,16 @@
 __setup("swiotlb=", setup_io_tlb_npages);
 /* make io_tlb_overflow tunable too? */
 
+void * __weak swiotlb_alloc_boot(size_t size, unsigned long nslabs)
+{
+	return alloc_bootmem_low_pages(size);
+}
+
+void * __weak swiotlb_alloc(unsigned order, unsigned long nslabs)
+{
+	return (void *)__get_free_pages(GFP_DMA | __GFP_NOWARN, order);
+}
+
 /*
  * Statically reserve bounce buffer space and initialize bounce buffer data
  * structures for the software IO TLB used to implement the DMA API.

@@ -145,7 +156,7 @@
 	/*
 	 * Get IO TLB memory from the low pages
 	 */
-	io_tlb_start = alloc_bootmem_low_pages(bytes);
+	io_tlb_start = swiotlb_alloc_boot(bytes, io_tlb_nslabs);
 	if (!io_tlb_start)
 		panic("Cannot allocate SWIOTLB buffer");
 	io_tlb_end = io_tlb_start + bytes;

@@ -202,8 +213,7 @@
 	bytes = io_tlb_nslabs << IO_TLB_SHIFT;
 
 	while ((SLABS_PER_PAGE << order) > IO_TLB_MIN_SLABS) {
-		io_tlb_start = (char *)__get_free_pages(GFP_DMA | __GFP_NOWARN,
-		                                        order);
+		io_tlb_start = swiotlb_alloc(order, io_tlb_nslabs);
 		if (io_tlb_start)
 			break;
 		order--;

@@ -10,6 +10,9 @@
 extern void
 swiotlb_init(void);
 
+extern void *swiotlb_alloc_boot(size_t bytes, unsigned long nslabs);
+extern void *swiotlb_alloc(unsigned order, unsigned long nslabs);
+
 extern void
 *swiotlb_alloc_coherent(struct device *hwdev, size_t size,
 			dma_addr_t *dma_handle, gfp_t flags);

@@ -21,6 +21,7 @@
 #include <linux/mm.h>
 #include <linux/module.h>
 #include <linux/spinlock.h>
+#include <linux/swiotlb.h>
 #include <linux/string.h>
 #include <linux/types.h>
 #include <linux/ctype.h>

@@ -126,6 +127,16 @@
 __setup("swiotlb=", setup_io_tlb_npages);
 /* make io_tlb_overflow tunable too? */
 
+void * __weak swiotlb_alloc_boot(size_t size, unsigned long nslabs)
+{
+	return alloc_bootmem_low_pages(size);
+}
+
+void * __weak swiotlb_alloc(unsigned order, unsigned long nslabs)
+{
+	return (void *)__get_free_pages(GFP_DMA | __GFP_NOWARN, order);
+}
+
 /*
  * Statically reserve bounce buffer space and initialize bounce buffer data
  * structures for the software IO TLB used to implement the DMA API.

@@ -145,7 +156,7 @@
 	/*
 	 * Get IO TLB memory from the low pages
 	 */
-	io_tlb_start = alloc_bootmem_low_pages(bytes);
+	io_tlb_start = swiotlb_alloc_boot(bytes, io_tlb_nslabs);
 	if (!io_tlb_start)
 		panic("Cannot allocate SWIOTLB buffer");
 	io_tlb_end = io_tlb_start + bytes;

@@ -202,8 +213,7 @@
 	bytes = io_tlb_nslabs << IO_TLB_SHIFT;
 
 	while ((SLABS_PER_PAGE << order) > IO_TLB_MIN_SLABS) {
-		io_tlb_start = (char *)__get_free_pages(GFP_DMA | __GFP_NOWARN,
-		                                        order);
+		io_tlb_start = swiotlb_alloc(order, io_tlb_nslabs);
 		if (io_tlb_start)
 			break;
 		order--;

@@ -7,6 +7,20 @@
 struct dma_attrs;
 struct scatterlist;
 
+/*
+ * Maximum allowable number of contiguous slabs to map,
+ * must be a power of 2.  What is the appropriate value ?
+ * The complexity of {map,unmap}_single is linearly dependent on this value.
+ */
+#define IO_TLB_SEGSIZE	128
+
+
+/*
+ * log of the size of each IO TLB slab.  The number of slabs is command line
+ * controllable.
+ */
+#define IO_TLB_SHIFT 11
+
 extern void
 swiotlb_init(void);
 

@@ -23,6 +23,7 @@
 #include <linux/spinlock.h>
 #include <linux/swiotlb.h>
 #include <linux/string.h>
+#include <linux/swiotlb.h>
 #include <linux/types.h>
 #include <linux/ctype.h>
 

@@ -40,19 +41,6 @@
 #define SG_ENT_VIRT_ADDRESS(sg)	(sg_virt((sg)))
 #define SG_ENT_PHYS_ADDRESS(sg)	virt_to_bus(SG_ENT_VIRT_ADDRESS(sg))
 
-/*
- * Maximum allowable number of contiguous slabs to map,
- * must be a power of 2.  What is the appropriate value ?
- * The complexity of {map,unmap}_single is linearly dependent on this value.
- */
-#define IO_TLB_SEGSIZE	128
-
-/*
- * log of the size of each IO TLB slab.  The number of slabs is command line
- * controllable.
- */
-#define IO_TLB_SHIFT 11
-
 #define SLABS_PER_PAGE (1 << (PAGE_SHIFT - IO_TLB_SHIFT))
 
 /*

@@ -28,12 +28,7 @@
 
 void *swiotlb_alloc(unsigned order, unsigned long nslabs)
 {
-	void *ret = (void *)__get_free_pages(GFP_DMA | __GFP_NOWARN, order);
-
-	if (ret && xen_pv_domain())
-		xen_swiotlb_fixup(ret, 1u << order, nslabs);
-
-	return ret;
+	BUG();
 }
 
 static dma_addr_t

@@ -6,6 +6,7 @@
 #include <linux/version.h>
 #include <linux/scatterlist.h>
 #include <linux/bio.h>
+#include <linux/swiotlb.h>
 #include <linux/io.h>
 #include <linux/bug.h>
 

@@ -43,19 +44,27 @@
 	unsigned long	*bitmap;
 };
 
+static int max_dma_bits = 32;
+
 void xen_swiotlb_fixup(void *buf, size_t size, unsigned long nslabs)
 {
-	unsigned order = get_order(size);
+	int i, rc;
+	int dma_bits;
 
-	printk(KERN_DEBUG "xen_swiotlb_fixup: buf=%p size=%zu order=%u\n",
-		buf, size, order);
+	printk(KERN_DEBUG "xen_swiotlb_fixup: buf=%p size=%zu\n",
+		buf, size);
 
-	if (WARN_ON(size != (PAGE_SIZE << order)))
-		return;
-
-	if (xen_create_contiguous_region((unsigned long)buf,
-					 order, 0xffffffff))
-		printk(KERN_ERR "xen_create_contiguous_region failed\n");
+	dma_bits = get_order(IO_TLB_SEGSIZE << IO_TLB_SHIFT) + PAGE_SHIFT;
+	for (i = 0; i < nslabs; i += IO_TLB_SEGSIZE) {
+		do {
+			rc = xen_create_contiguous_region(
+				(unsigned long)buf + (i << IO_TLB_SHIFT),
+				get_order(IO_TLB_SEGSIZE << IO_TLB_SHIFT),
+				dma_bits);
+		} while (rc && dma_bits++ < max_dma_bits);
+		if (rc)
+			panic(KERN_ERR "xen_create_contiguous_region failed\n");
+	}
 }
 
 static inline int address_needs_mapping(struct device *hwdev,

@@ -117,7 +126,8 @@
 	if (check_pages_physically_contiguous(pfn, offset, size))
 		return 0;
 
-	printk("range_straddles_page_boundary: p=%Lx size=%d pfn=%lx\n",
+	printk(KERN_WARNING "range_straddles_page_boundary: "
+	       "p=%Lx size=%zd pfn=%lx\n",
 		p, size, pfn);
 	return 1;
 }

@@ -27,6 +27,9 @@
 extern void *swiotlb_alloc_boot(size_t bytes, unsigned long nslabs);
 extern void *swiotlb_alloc(unsigned order, unsigned long nslabs);
 
+extern unsigned long __weak swiotlb_virt_to_bus(volatile void *address);
+extern void * __weak swiotlb_bus_to_virt(unsigned long address);
+
 extern void
 *swiotlb_alloc_coherent(struct device *hwdev, size_t size,
 			dma_addr_t *dma_handle, gfp_t flags);

144 lines not on this page · raw message

@@ -33,8 +33,14 @@
 #ifndef _ASM_X86_XEN_HYPERCALL_H
 #define _ASM_X86_XEN_HYPERCALL_H
 
+#include <linux/kernel.h>
+#include <linux/spinlock.h>
 #include <linux/errno.h>
 #include <linux/string.h>
+#include <linux/types.h>
+
+#include <asm/page.h>
+#include <asm/pgtable.h>
 
 #include <xen/interface/xen.h>
 #include <xen/interface/sched.h>

@@ -33,39 +33,10 @@
 #ifndef _ASM_X86_XEN_HYPERVISOR_H
 #define _ASM_X86_XEN_HYPERVISOR_H
 
-#include <linux/types.h>
-#include <linux/kernel.h>
-
-#include <xen/interface/xen.h>
-#include <xen/interface/version.h>
-
-#include <asm/ptrace.h>
-#include <asm/page.h>
-#include <asm/desc.h>
-#if defined(__i386__)
-#  ifdef CONFIG_X86_PAE
-#   include <asm-generic/pgtable-nopud.h>
-#  else
-#   include <asm-generic/pgtable-nopmd.h>
-#  endif
-#endif
-#include <asm/xen/hypercall.h>
-
 /* arch/i386/kernel/setup.c */
 extern struct shared_info *HYPERVISOR_shared_info;
 extern struct start_info *xen_start_info;
 
-/* arch/i386/mach-xen/evtchn.c */
-/* Force a proper event-channel callback from Xen. */
-extern void force_evtchn_callback(void);
-
-/* Turn jiffies into Xen system time. */
-u64 jiffies_to_st(unsigned long jiffies);
-
-
-#define MULTI_UVMFLAGS_INDEX 3
-#define MULTI_UVMDOMID_INDEX 4
-
 enum xen_domain_type {
 	XEN_NATIVE,
 	XEN_PV_DOMAIN,

@@ -74,9 +45,15 @@
 
 extern enum xen_domain_type xen_domain_type;
 
+#ifdef CONFIG_XEN
 #define xen_domain()		(xen_domain_type != XEN_NATIVE)
-#define xen_pv_domain()		(xen_domain_type == XEN_PV_DOMAIN)
+#else
+#define xen_domain()		(0)
+#endif
+
+#define xen_pv_domain()		(xen_domain() && xen_domain_type == XEN_PV_DOMAIN)
+#define xen_hvm_domain()	(xen_domain() && xen_domain_type == XEN_HVM_DOMAIN)
+
 #define xen_initial_domain()	(xen_pv_domain() && xen_start_info->flags & SIF_INITDOMAIN)
-#define xen_hvm_domain()	(xen_domain_type == XEN_HVM_DOMAIN)
 
 #endif /* _ASM_X86_XEN_HYPERVISOR_H */

@@ -1,11 +1,16 @@
 #ifndef _ASM_X86_XEN_PAGE_H
 #define _ASM_X86_XEN_PAGE_H
 
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/spinlock.h>
 #include <linux/pfn.h>
 
 #include <asm/uaccess.h>
+#include <asm/page.h>
 #include <asm/pgtable.h>
 
+#include <xen/interface/xen.h>
 #include <xen/features.h>
 
 /* Xen machine address */

@@ -28,6 +28,7 @@
 #include <linux/console.h>
 
 #include <xen/interface/xen.h>
+#include <xen/interface/version.h>
 #include <xen/interface/physdev.h>
 #include <xen/interface/vcpu.h>
 #include <xen/features.h>

@@ -44,13 +44,15 @@
 #include <linux/list.h>
 #include <linux/sysdev.h>
 
-#include <asm/xen/hypervisor.h>
 #include <asm/page.h>
 #include <asm/pgalloc.h>
 #include <asm/pgtable.h>
 #include <asm/uaccess.h>
 #include <asm/tlb.h>
 
+#include <asm/xen/hypervisor.h>
+#include <asm/xen/hypercall.h>
+#include <xen/interface/xen.h>
 #include <xen/interface/memory.h>
 #include <xen/xenbus.h>
 #include <xen/features.h>

@@ -8,7 +8,11 @@
 #include <linux/types.h>
 #include <linux/cache.h>
 #include <linux/module.h>
-#include <asm/xen/hypervisor.h>
+
+#include <asm/xen/hypercall.h>
+
+#include <xen/interface/xen.h>
+#include <xen/interface/version.h>
 #include <xen/features.h>
 
 u8 xen_features[XENFEAT_NR_SUBMAPS * 32] __read_mostly;

@@ -40,6 +40,7 @@
 #include <xen/interface/xen.h>
 #include <xen/page.h>
 #include <xen/grant_table.h>
+#include <asm/xen/hypercall.h>
 
 #include <asm/pgtable.h>
 #include <asm/sync_bitops.h>

@@ -9,6 +9,8 @@
 #ifndef __XEN_PUBLIC_EVENT_CHANNEL_H__
 #define __XEN_PUBLIC_EVENT_CHANNEL_H__
 
+#include <xen/interface/xen.h>
+
 typedef uint32_t evtchn_port_t;
 DEFINE_GUEST_HANDLE(evtchn_port_t);
 

@@ -21,6 +21,15 @@
 #define IO_APIC_REDIR_LEVEL_TRIGGER	(1 << 15)
 #define IO_APIC_REDIR_MASKED		(1 << 16)
 
+struct io_apic_ops {
+	void (*init)(void);
+	unsigned int (*read)(unsigned int apic, unsigned int reg);
+	void (*write)(unsigned int apic, unsigned int reg, unsigned int value);
+	void (*modify)(unsigned int apic, unsigned int reg, unsigned int value);
+};
+
+void __init set_io_apic_ops(const struct io_apic_ops *);
+
 /*
  * The structure of the IO-APIC:
  */

86 lines not on this page · raw message

@@ -125,12 +125,35 @@
 
 extern struct apic_ops *apic_ops;
 
-#define apic_read (apic_ops->read)
-#define apic_write (apic_ops->write)
-#define apic_icr_read (apic_ops->icr_read)
-#define apic_icr_write (apic_ops->icr_write)
-#define apic_wait_icr_idle (apic_ops->wait_icr_idle)
-#define safe_apic_wait_icr_idle (apic_ops->safe_wait_icr_idle)
+static inline u32 apic_read(u32 reg)
+{
+	return apic_ops->read(reg);
+}
+
+static inline void apic_write(u32 reg, u32 val)
+{
+	apic_ops->write(reg, val);
+}
+
+static inline u64 apic_icr_read(void)
+{
+	return apic_ops->icr_read();
+}
+
+static inline void apic_icr_write(u32 low, u32 high)
+{
+	apic_ops->icr_write(low, high);
+}
+
+static inline void apic_wait_icr_idle(void)
+{
+	apic_ops->wait_icr_idle();
+}
+
+static inline u32 safe_apic_wait_icr_idle(void)
+{
+	return apic_ops->safe_wait_icr_idle();
+}
 
 extern int get_physical_broadcast(void);
 

@@ -834,10 +834,11 @@
 
 		hpet_address = force_hpet_address;
 		hpet_enable();
-		if (!hpet_virt_address)
-			return -ENODEV;
 	}
 
+	if (!hpet_virt_address)
+		return -ENODEV;
+
 	hpet_reserve_platform_timers(hpet_readl(HPET_ID));
 
 	for_each_online_cpu(cpu) {

@@ -39,6 +39,7 @@
 extern unsigned int do_IRQ(struct pt_regs *regs);
 extern void init_IRQ(void);
 extern void native_init_IRQ(void);
+extern bool handle_irq(unsigned irq, struct pt_regs *regs);
 
 /* Interrupt vector management */
 extern DECLARE_BITMAP(used_vectors, NR_VECTORS);

@@ -191,6 +191,26 @@
 execute_on_irq_stack(int overflow, struct irq_desc *desc, int irq) { return 0; }
 #endif
 
+bool handle_irq(unsigned irq, struct pt_regs *regs)
+{
+	struct irq_desc *desc;
+	int overflow;
+
+	overflow = check_stack_overflow();
+
+	desc = irq_to_desc(irq);
+	if (unlikely(!desc))
+		return false;
+
+	if (!execute_on_irq_stack(overflow, desc, irq)) {
+		if (unlikely(overflow))
+			print_stack_overflow();
+		desc->handle_irq(irq, desc);
+	}
+
+	return true;
+}
+
 /*
  * do_IRQ handles all normal device IRQ's (the special
  * SMP cross-CPU interrupts have their own specific

@@ -200,31 +220,19 @@
 {
 	struct pt_regs *old_regs;
 	/* high bit used in ret_from_ code */
-	int overflow;
 	unsigned vector = ~regs->orig_ax;
-	struct irq_desc *desc;
 	unsigned irq;
 
-
 	old_regs = set_irq_regs(regs);
 	irq_enter();
 	irq = __get_cpu_var(vector_irq)[vector];
 
-	overflow = check_stack_overflow();
-
-	desc = irq_to_desc(irq);
-	if (unlikely(!desc)) {
+	if (!handle_irq(irq, regs)) {
 		printk(KERN_EMERG "%s: cannot handle IRQ %d vector %#x cpu %d\n",
 					__func__, irq, vector, smp_processor_id());
 		BUG();
 	}
 
-	if (!execute_on_irq_stack(overflow, desc, irq)) {
-		if (unlikely(overflow))
-			print_stack_overflow();
-		desc->handle_irq(irq, desc);
-	}
-
 	irq_exit();
 	set_irq_regs(old_regs);
 	return 1;

@@ -42,6 +42,22 @@
 }
 #endif
 
+bool handle_irq(unsigned irq, struct pt_regs *regs)
+{
+	struct irq_desc *desc;
+
+#ifdef CONFIG_DEBUG_STACKOVERFLOW
+	stack_overflow_check(regs);
+#endif
+
+	desc = irq_to_desc(irq);
+	if (unlikely(!desc))
+		return false;
+
+	generic_handle_irq_desc(irq, desc);
+	return true;
+}
+
 /*
  * do_IRQ handles all normal device IRQ's (the special
  * SMP cross-CPU interrupts have their own specific

@@ -50,7 +66,6 @@
 asmlinkage unsigned int do_IRQ(struct pt_regs *regs)
 {
 	struct pt_regs *old_regs = set_irq_regs(regs);
-	struct irq_desc *desc;
 
 	/* high bit used in ret_from_ code  */
 	unsigned vector = ~regs->orig_ax;

@@ -58,16 +73,10 @@
 
 	exit_idle();
 	irq_enter();
+
 	irq = __get_cpu_var(vector_irq)[vector];
 
-#ifdef CONFIG_DEBUG_STACKOVERFLOW
-	stack_overflow_check(regs);
-#endif
-
-	desc = irq_to_desc(irq);
-	if (likely(desc))
-		generic_handle_irq_desc(irq, desc);
-	else {
+	if (!handle_irq(irq, regs)) {
 		if (!disable_apic)
 			ack_APIC_irq();
 

@@ -8,8 +8,18 @@
 void idle_notifier_register(struct notifier_block *n);
 void idle_notifier_unregister(struct notifier_block *n);
 
+#ifdef CONFIG_X86_64
 void enter_idle(void);
 void exit_idle(void);
+#else
+static inline void enter_idle(void)
+{
+}
+
+static inline void exit_idle(void)
+{
+}
+#endif	/* CONFIG_X86_64 */
 
 void c1e_remove_cpu(int cpu);
 

@@ -808,9 +808,8 @@
 	 * Besides, if we don't timer interrupts ignore the global
 	 * interrupt lock, which is the WrongThing (tm) to do.
 	 */
-#ifdef CONFIG_X86_64
 	exit_idle();
-#endif
+
 	irq_enter();
 	local_apic_timer_interrupt();
 	irq_exit();

@@ -1668,9 +1667,7 @@
 {
 	u32 v;
 
-#ifdef CONFIG_X86_64
 	exit_idle();
-#endif
 	irq_enter();
 	/*
 	 * Check if this really is a spurious interrupt and ACK it

@@ -1699,9 +1696,7 @@
 {
 	u32 v, v1;
 
-#ifdef CONFIG_X86_64
 	exit_idle();
-#endif
 	irq_enter();
 	/* First tickle the hardware, only then report what went on. -- REW */
 	v = apic_read(APIC_ESR);

@@ -2242,9 +2242,7 @@
 {
 	unsigned vector, me;
 	ack_APIC_irq();
-#ifdef CONFIG_X86_64
 	exit_idle();
-#endif
 	irq_enter();
 
 	me = smp_processor_id();

@@ -46,6 +46,8 @@
 extern enum xen_domain_type xen_domain_type;
 
 #ifdef CONFIG_XEN
+#include <xen/interface/xen.h>
+
 #define xen_domain()		(xen_domain_type != XEN_NATIVE)
 #else
 #define xen_domain()		(0)

@@ -42,6 +42,8 @@
 #include <asm/mpspec.h>
 #include <asm/smp.h>
 
+#include <asm/xen/hypervisor.h>
+
 #ifdef CONFIG_X86_LOCAL_APIC
 # include <mach_apic.h>
 #endif

@@ -234,6 +236,10 @@
 {
 	unsigned int ver = 0;
 
+	/* We don't want to register lapics when in Xen dom0 */
+	if (xen_initial_domain())
+		return;
+
 	if (!enabled) {
 		++disabled_cpus;
 		return;

@@ -755,6 +761,10 @@
 
 static void __init acpi_register_lapic_address(unsigned long address)
 {
+	/* Xen dom0 doesn't have usable lapics */
+	if (xen_initial_domain())
+		return;
+
 	mp_lapic_addr = address;
 
 	set_fixmap_nocache(FIX_APIC_BASE, address);

@@ -63,6 +63,7 @@
 #ifdef CONFIG_X86_IO_APIC
 extern int mp_config_acpi_gsi(unsigned char number, unsigned int devfn, u8 pin,
 				u32 gsi, int triggering, int polarity);
+extern int mp_find_ioapic(int gsi);
 #else
 static inline int
 mp_config_acpi_gsi(unsigned char number, unsigned int devfn, u8 pin,

@@ -865,7 +865,7 @@
 	DECLARE_BITMAP(pin_programmed, MP_MAX_IOAPIC_PIN + 1);
 } mp_ioapic_routing[MAX_IO_APICS];
 
-static int mp_find_ioapic(int gsi)
+int mp_find_ioapic(int gsi)
 {
 	int i = 0;
 

@@ -64,6 +64,7 @@
 extern int mp_config_acpi_gsi(unsigned char number, unsigned int devfn, u8 pin,
 				u32 gsi, int triggering, int polarity);
 extern int mp_find_ioapic(int gsi);
+extern int mp_find_ioapic_pin(int ioapic, int gsi);
 #else
 static inline int
 mp_config_acpi_gsi(unsigned char number, unsigned int devfn, u8 pin,

@@ -880,6 +880,16 @@
 	return -1;
 }
 
+int mp_find_ioapic_pin(int ioapic, int gsi)
+{
+	if (WARN_ON(ioapic == -1))
+		return -1;
+	if (WARN_ON(gsi > mp_ioapic_routing[ioapic].gsi_end))
+		return -1;
+
+	return gsi - mp_ioapic_routing[ioapic].gsi_base;
+}
+
 static u8 __init uniq_ioapic_id(u8 id)
 {
 #ifdef CONFIG_X86_32

@@ -992,7 +1002,7 @@
 	ioapic = mp_find_ioapic(gsi);
 	if (ioapic < 0)
 		return;
-	pin = gsi - mp_ioapic_routing[ioapic].gsi_base;
+	pin = mp_find_ioapic_pin(ioapic, gsi);
 
 	/*
 	 * TBD: This check is for faulty timer entries, where the override

@@ -1114,7 +1124,7 @@
 		return gsi;
 	}
 
-	ioapic_pin = gsi - mp_ioapic_routing[ioapic].gsi_base;
+	ioapic_pin = mp_find_ioapic_pin(ioapic, gsi);
 
 #ifdef CONFIG_X86_32
 	if (ioapic_renumber_irq)

@@ -1203,7 +1213,7 @@
 	mp_irq.mp_srcbusirq = (((devfn >> 3) & 0x1f) << 2) | ((pin - 1) & 3);
 	ioapic = mp_find_ioapic(gsi);
 	mp_irq.mp_dstapic = mp_ioapic_routing[ioapic].apic_id;
-	mp_irq.mp_dstirq = gsi - mp_ioapic_routing[ioapic].gsi_base;
+	mp_irq.mp_dstirq = mp_find_ioapic_pin(ioapic, gsi);
 
 	save_mp_irq(&mp_irq);
 #endif

@@ -209,6 +209,12 @@
 
 extern int probe_nr_irqs(void);
 
+extern int setup_ioapic_entry(int apic, int irq,
+			      struct IO_APIC_route_entry *entry,
+			      unsigned int destination, int trigger,
+			      int polarity, int vector);
+extern void ioapic_write_entry(int apic, int pin,
+			       struct IO_APIC_route_entry e);
 #else  /* !CONFIG_X86_IO_APIC */
 #define io_apic_assign_pci_irqs 0
 static const int timer_through_8259 = 0;

@@ -337,7 +337,7 @@
 	io_apic_write(apic, 0x10 + 2*pin, eu.w1);
 }
 
-static void ioapic_write_entry(int apic, int pin, struct IO_APIC_route_entry e)
+void ioapic_write_entry(int apic, int pin, struct IO_APIC_route_entry e)
 {
 	unsigned long flags;
 	spin_lock_irqsave(&ioapic_lock, flags);

@@ -1275,10 +1275,10 @@
 					      handle_edge_irq, "edge");
 }
 
-static int setup_ioapic_entry(int apic, int irq,
-			      struct IO_APIC_route_entry *entry,
-			      unsigned int destination, int trigger,
-			      int polarity, int vector)
+int setup_ioapic_entry(int apic, int irq,
+		       struct IO_APIC_route_entry *entry,
+		       unsigned int destination, int trigger,
+		       int polarity, int vector)
 {
 	/*
 	 * add it to the IO-APIC irq-routing table:

@@ -1,6 +1,7 @@
 #ifndef _ASM_X86_NUMA_64_H
 #define _ASM_X86_NUMA_64_H
 
+#include <linux/init.h>
 #include <linux/nodemask.h>
 #include <asm/apicdef.h>
 

@@ -3,6 +3,8 @@
 #include <linux/pci.h>
 #include <linux/cache.h>
 #include <linux/module.h>
+#include <linux/swiotlb.h>
+#include <linux/bootmem.h>
 #include <linux/dma-mapping.h>
 
 #include <asm/iommu.h>

@@ -11,6 +13,16 @@
 
 int swiotlb __read_mostly;
 
+void *swiotlb_alloc_boot(size_t size, unsigned long nslabs)
+{
+	return alloc_bootmem_low_pages(size);
+}
+
+void *swiotlb_alloc(unsigned order, unsigned long nslabs)
+{
+	return (void *)__get_free_pages(GFP_DMA | __GFP_NOWARN, order);
+}
+
 static dma_addr_t
 swiotlb_map_single_phys(struct device *hwdev, phys_addr_t paddr, size_t size,
 			int direction)

@@ -66,21 +66,17 @@
 		return dma_ops;
 	else
 		return dev->archdata.dma_ops;
-#endif /* _ASM_X86_DMA_MAPPING_H */
+#endif
 }
 
 /* Make sure we keep the same behaviour */
 static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
 {
-#ifdef CONFIG_X86_32
-	return 0;
-#else
 	struct dma_mapping_ops *ops = get_dma_ops(dev);
 	if (ops->mapping_error)
 		return ops->mapping_error(dev, dma_addr);
 
 	return (dma_addr == bad_dma_address);
-#endif
 }
 
 #define dma_alloc_noncoherent(d, s, h, f) dma_alloc_coherent(d, s, h, f)

@@ -84,6 +84,8 @@
 static inline void early_quirks(void) { }
 #endif
 
+extern void pci_iommu_alloc(void);
+
 #endif  /* __KERNEL__ */
 
 #ifdef CONFIG_X86_32

@@ -23,7 +23,6 @@
 			       int reg, int len, u32 value);
 
 extern void dma32_reserve_bootmem(void);
-extern void pci_iommu_alloc(void);
 
 /* The PCI address space does equal the physical memory
  * address space.  The networking and block device layers use

@@ -105,11 +105,15 @@
 	dma32_bootmem_ptr = NULL;
 	dma32_bootmem_size = 0;
 }
+#endif
 
 void __init pci_iommu_alloc(void)
 {
+#ifdef CONFIG_X86_64
 	/* free the range so iommu could get some range less than 4G */
 	dma32_free_bootmem();
+#endif
+
 	/*
 	 * The order of these functions is important for
 	 * fall-back/fail-over reasons

@@ -125,8 +129,6 @@
 	pci_swiotlb_init();
 }
 
-#endif
-
 void *dma_generic_alloc_coherent(struct device *dev, size_t size,
 				 dma_addr_t *dma_addr, gfp_t flag)
 {

@@ -62,8 +62,10 @@
 void __init pci_swiotlb_init(void)
 {
 	/* don't initialize swiotlb if iommu=off (no_iommu=1) */
+#ifdef CONFIG_X86_64
 	if (!iommu_detected && !no_iommu && max_pfn > MAX_DMA32_PFN)
 	       swiotlb = 1;
+#endif
 	if (swiotlb_force)
 		swiotlb = 1;
 	if (swiotlb) {

@@ -21,6 +21,7 @@
 #include <linux/init.h>
 #include <linux/highmem.h>
 #include <linux/pagemap.h>
+#include <linux/pci.h>
 #include <linux/pfn.h>
 #include <linux/poison.h>
 #include <linux/bootmem.h>

@@ -971,6 +972,8 @@
 	int codesize, reservedpages, datasize, initsize;
 	int tmp;
 
+	pci_iommu_alloc();
+
 #ifdef CONFIG_FLATMEM
 	BUG_ON(!mem_map);
 #endif

diff -r 5fa30e5284dd lib/swiotlb.c
@@ -303,7 +303,7 @@
 	unsigned int nslots, stride, index, wrap;
 	int i;
 	unsigned long start_dma_addr;
-	unsigned long mask;
+	u64 mask;
 	unsigned long offset_slots;
 	unsigned long max_slots;
 

@@ -314,6 +314,7 @@
 	max_slots = mask + 1
 		    ? ALIGN(mask + 1, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT
 		    : 1UL << (BITS_PER_LONG - IO_TLB_SHIFT);
+	BUG_ON(max_slots > 1UL << (BITS_PER_LONG - IO_TLB_SHIFT));
 
 	/*
 	 * For mappings greater than a page, we limit the stride (and

@@ -23,6 +23,16 @@
 	return (void *)__get_free_pages(GFP_DMA | __GFP_NOWARN, order);
 }
 
+unsigned long swiotlb_virt_to_bus(volatile void *address)
+{
+	return virt_to_bus(address);
+}
+
+void * swiotlb_bus_to_virt(unsigned long address)
+{
+	return bus_to_virt(address);
+}
+
 static dma_addr_t
 swiotlb_map_single_phys(struct device *hwdev, phys_addr_t paddr, size_t size,
 			int direction)

@@ -55,7 +55,7 @@
 	notify_remote_via_evtchn(xen_start_info->console.domU.evtchn);
 }
 
-static int write_console(uint32_t vtermno, const char *data, int len)
+static int domU_write_console(uint32_t vtermno, const char *data, int len)
 {
 	struct xencons_interface *intf = xencons_interface();
 	XENCONS_RING_IDX cons, prod;

@@ -76,7 +76,7 @@
 	return sent;
 }
 
-static int read_console(uint32_t vtermno, char *buf, int len)
+static int domU_read_console(uint32_t vtermno, char *buf, int len)
 {
 	struct xencons_interface *intf = xencons_interface();
 	XENCONS_RING_IDX cons, prod;

@@ -97,28 +97,62 @@
 	return recv;
 }
 
-static struct hv_ops hvc_ops = {
-	.get_chars = read_console,
-	.put_chars = write_console,
+static struct hv_ops domU_hvc_ops = {
+	.get_chars = domU_read_console,
+	.put_chars = domU_write_console,
 	.notifier_add = notifier_add_irq,
 	.notifier_del = notifier_del_irq,
 	.notifier_hangup = notifier_hangup_irq,
 };
 
-static int __init xen_init(void)
+static int dom0_read_console(uint32_t vtermno, char *buf, int len)
+{
+	return HYPERVISOR_console_io(CONSOLEIO_read, len, buf);
+}
+
+/*
+ * Either for a dom0 to write to the system console, or a domU with a
+ * debug version of Xen
+ */
+static int dom0_write_console(uint32_t vtermno, const char *str, int len)
+{
+	int rc = HYPERVISOR_console_io(CONSOLEIO_write, len, (char *)str);
+	if (rc < 0)
+		return 0;
+
+	return len;
+}
+
+static struct hv_ops dom0_hvc_ops = {
+	.get_chars = dom0_read_console,
+	.put_chars = dom0_write_console,
+	.notifier_add = notifier_add_irq,
+	.notifier_del = notifier_del_irq,
+};
+
+static int __init xen_hvc_init(void)
 {
 	struct hvc_struct *hp;
+	struct hv_ops *ops;
 
-	if (!xen_pv_domain() ||
-	    xen_initial_domain() ||
-	    !xen_start_info->console.domU.evtchn)
-		return -ENODEV;
+	if (!xen_pv_domain())
+ 		return -ENODEV;
 
-	xencons_irq = bind_evtchn_to_irq(xen_start_info->console.domU.evtchn);
+	if (xen_initial_domain()) {
+		ops = &dom0_hvc_ops;
+		xencons_irq = bind_virq_to_irq(VIRQ_CONSOLE, 0);
+	} else {
+		if (!xen_start_info->console.domU.evtchn)
+			return -ENODEV;
+
+		ops = &domU_hvc_ops;
+		xencons_irq = bind_evtchn_to_irq(xen_start_info->console.domU.evtchn);
+	}
+
 	if (xencons_irq < 0)
 		xencons_irq = 0; /* NO_IRQ */
 
-	hp = hvc_alloc(HVC_COOKIE, xencons_irq, &hvc_ops, 256);
+	hp = hvc_alloc(HVC_COOKIE, xencons_irq, ops, 256);
 	if (IS_ERR(hp))
 		return PTR_ERR(hp);
 

@@ -135,7 +169,7 @@
 		rebind_evtchn_irq(xen_start_info->console.domU.evtchn, xencons_irq);
 }
 
-static void __exit xen_fini(void)
+static void __exit xen_hvc_fini(void)
 {
 	if (hvc)
 		hvc_remove(hvc);

@@ -143,29 +177,24 @@
 
 static int xen_cons_init(void)
 {
+	struct hv_ops *ops;
+
 	if (!xen_pv_domain())
 		return 0;
 
-	hvc_instantiate(HVC_COOKIE, 0, &hvc_ops);
+	ops = &domU_hvc_ops;
+	if (xen_initial_domain())
+		ops = &dom0_hvc_ops;
+
+	hvc_instantiate(HVC_COOKIE, 0, ops);
+
 	return 0;
 }
 
-module_init(xen_init);
-module_exit(xen_fini);
+module_init(xen_hvc_init);
+module_exit(xen_hvc_fini);
 console_initcall(xen_cons_init);
 
-static void raw_console_write(const char *str, int len)
-{
-	while(len > 0) {
-		int rc = HYPERVISOR_console_io(CONSOLEIO_write, len, (char *)str);
-		if (rc <= 0)
-			break;
-
-		str += rc;
-		len -= rc;
-	}
-}
-
 #ifdef CONFIG_EARLY_PRINTK
 static void xenboot_write_console(struct console *console, const char *string,
 				  unsigned len)

@@ -173,19 +202,22 @@
 	unsigned int linelen, off = 0;
 	const char *pos;
 
-	raw_console_write(string, len);
+	dom0_write_console(0, string, len);
 
-	write_console(0, "(early) ", 8);
+	if (xen_initial_domain())
+		return;
+
+	domU_write_console(0, "(early) ", 8);
 	while (off < len && NULL != (pos = strchr(string+off, '\n'))) {
 		linelen = pos-string+off;
 		if (off + linelen > len)
 			break;
-		write_console(0, string+off, linelen);
-		write_console(0, "\r\n", 2);
+		domU_write_console(0, string+off, linelen);
+		domU_write_console(0, "\r\n", 2);
 		off += linelen + 1;
 	}
 	if (off < len)
-		write_console(0, string+off, len-off);
+		domU_write_console(0, string+off, len-off);
 }
 
 struct console xenboot_console = {

@@ -197,7 +229,7 @@
 
 void xen_raw_console_write(const char *str)
 {
-	raw_console_write(str, strlen(str));
+	dom0_write_console(0, str, strlen(str));
 }
 
 void xen_raw_printk(const char *fmt, ...)

@@ -307,7 +307,7 @@
 }
 
 
-static int bind_virq_to_irq(unsigned int virq, unsigned int cpu)
+int bind_virq_to_irq(unsigned int virq, unsigned int cpu)
 {
 	struct evtchn_bind_virq bind_virq;
 	int evtchn, irq;

@@ -12,6 +12,8 @@
 			      irq_handler_t handler,
 			      unsigned long irqflags, const char *devname,
 			      void *dev_id);
+int bind_virq_to_irq(unsigned int virq, unsigned int cpu);
+
 int bind_virq_to_irqhandler(unsigned int virq, unsigned int cpu,
 			    irq_handler_t handler,
 			    unsigned long irqflags, const char *devname,

@@ -810,6 +810,7 @@
 static int __init xenbus_probe_init(void)
 {
 	int err = 0;
+	unsigned long page = 0;
 
 	DPRINTK("");
 

@@ -830,7 +831,31 @@
 	 * Domain0 doesn't have a store_evtchn or store_mfn yet.
 	 */
 	if (xen_initial_domain()) {
-		/* dom0 not yet supported */
+		struct evtchn_alloc_unbound alloc_unbound;
+
+		/* Allocate Xenstore page */
+		page = get_zeroed_page(GFP_KERNEL);
+		if (!page)
+			return -ENOMEM;
+
+		xen_store_mfn = xen_start_info->store_mfn =
+			pfn_to_mfn(virt_to_phys((void *)page) >>
+				   PAGE_SHIFT);
+
+		/* Next allocate a local port which xenstored can bind to */
+		alloc_unbound.dom        = DOMID_SELF;
+		alloc_unbound.remote_dom = 0;
+
+		err = HYPERVISOR_event_channel_op(EVTCHNOP_alloc_unbound,
+						  &alloc_unbound);
+		if (err == -ENOSYS)
+			goto out_unreg_front;
+
+		BUG_ON(err);
+		xen_store_evtchn = xen_start_info->store_evtchn =
+			alloc_unbound.port;
+
+		xen_store_interface = mfn_to_virt(xen_store_mfn);
 	} else {
 		xenstored_ready = 1;
 		xen_store_evtchn = xen_start_info->store_evtchn;

@@ -858,6 +883,9 @@
 	bus_unregister(&xenbus_frontend.bus);
 
   out_error:
+	if (page != 0)
+		free_page(page);
+
 	return err;
 }
 

@@ -1437,6 +1437,7 @@
 	return __ka(m2p(maddr));
 }
 
+/* Set the page permissions on an identity-mapped pages */
 static void set_page_prot(void *addr, pgprot_t prot)
 {
 	unsigned long pfn = __pa(addr) >> PAGE_SHIFT;

@@ -1492,6 +1493,29 @@
 	set_page_prot(pmd, PAGE_KERNEL_RO);
 }
 
+static __init void xen_ident_map_ISA(void)
+{
+	unsigned long pa;
+
+	/*
+	 * If we're dom0, then linear map the ISA machine addresses into
+	 * the kernel's address space.
+	 */
+	if (!xen_initial_domain())
+		return;
+
+	xen_raw_printk("Xen: setup ISA identity maps\n");
+
+	for (pa = ISA_START_ADDRESS; pa < ISA_END_ADDRESS; pa += PAGE_SIZE) {
+		pte_t pte = mfn_pte(PFN_DOWN(pa), PAGE_KERNEL_IO);
+
+		if (HYPERVISOR_update_va_mapping(PAGE_OFFSET + pa, pte, 0))
+			BUG();
+	}
+
+	xen_flush_tlb();
+}
+
 #ifdef CONFIG_X86_64
 static void convert_pfn_mfn(void *v)
 {

@@ -1674,6 +1698,7 @@
 
 	xen_raw_console_write("mapping kernel into physical memory\n");
 	pgd = xen_setup_kernel_pagetable(pgd, xen_start_info->nr_pages);
+	xen_ident_map_ISA();
 
 	init_mm.pgd = pgd;
 

@@ -1683,6 +1708,13 @@
 	if (xen_feature(XENFEAT_supervisor_mode_kernel))
 		pv_info.kernel_rpl = 0;
 
+	if (xen_initial_domain()) {
+		struct physdev_set_iopl set_iopl;
+		set_iopl.iopl = 1;
+		if (HYPERVISOR_physdev_op(PHYSDEVOP_set_iopl, &set_iopl) == -1)
+			BUG();
+	}
+
 	/* set the limit of our address space */
 	xen_reserve_top();
 

@@ -51,6 +51,9 @@
 	 * Even though this is normal, usable memory under Xen, reserve
 	 * ISA memory anyway because too many things think they can poke
 	 * about in there.
+	 *
+	 * In a dom0 kernel, this region is identity mapped with the
+	 * hardware ISA area, so it really is out of bounds.
 	 */
 	e820_add_region(ISA_START_ADDRESS, ISA_END_ADDRESS - ISA_START_ADDRESS,
 			E820_RESERVED);

@@ -188,7 +191,8 @@
 
 	pm_idle = xen_idle;
 
-	paravirt_disable_iospace();
+	if (!xen_initial_domain())
+		paravirt_disable_iospace();
 
 	fiddle_vdso();
 }

@@ -205,18 +205,23 @@
 static void xen_cpuid(unsigned int *ax, unsigned int *bx,
 		      unsigned int *cx, unsigned int *dx)
 {
-	unsigned maskedx = ~0;
+	unsigned maskedx = 0;
 
 	/*
 	 * Mask out inconvenient features, to try and disable as many
 	 * unsupported kernel subsystems as possible.
 	 */
-	if (*ax == 1)
-		maskedx = ~((1 << X86_FEATURE_APIC) |  /* disable APIC */
-			    (1 << X86_FEATURE_ACPI) |  /* disable ACPI */
-			    (1 << X86_FEATURE_MCE)  |  /* disable MCE */
-			    (1 << X86_FEATURE_MCA)  |  /* disable MCA */
-			    (1 << X86_FEATURE_ACC));   /* thermal monitoring */
+	if (*ax == 1) {
+		maskedx =
+			(1 << X86_FEATURE_MCE)  |  /* disable MCE */
+			(1 << X86_FEATURE_MCA)  |  /* disable MCA */
+			(1 << X86_FEATURE_ACC);   /* thermal monitoring */
+
+		if (!xen_initial_domain())
+			maskedx |=
+				(1 << X86_FEATURE_APIC) |  /* disable local APIC */
+				(1 << X86_FEATURE_ACPI);  /* disable ACPI */
+	}
 
 	asm(XEN_EMULATE_PREFIX "cpuid"
 		: "=a" (*ax),

@@ -224,7 +229,7 @@
 		  "=c" (*cx),
 		  "=d" (*dx)
 		: "0" (*ax), "2" (*cx));
-	*dx &= maskedx;
+	*dx &= ~maskedx;
 }
 
 static void xen_set_debugreg(int reg, unsigned long val)

@@ -45,6 +45,7 @@
 #include <xen/interface/xen.h>
 #include <xen/interface/sched.h>
 #include <xen/interface/physdev.h>
+#include <xen/interface/platform.h>
 
 /*
  * The hypercall asms have to meet several constraints:

@@ -282,6 +283,13 @@
 }
 
 static inline int
+HYPERVISOR_dom0_op(struct xen_platform_op *platform_op)
+{
+	platform_op->interface_version = XENPF_INTERFACE_VERSION;
+	return _hypercall1(int, dom0_op, platform_op);
+}
+
+static inline int
 HYPERVISOR_set_debugreg(int reg, unsigned long value)
 {
 	return _hypercall2(int, set_debugreg, reg, value);

232 lines not on this page · raw message

@@ -461,6 +461,8 @@
 #define __mk_unsigned_long(x) x ## UL
 #define mk_unsigned_long(x) __mk_unsigned_long(x)
 
+DEFINE_GUEST_HANDLE(uint64_t);
+
 #else /* __ASSEMBLY__ */
 
 /* In assembly code we cannot use C numeric constant suffixes. */

@@ -108,6 +108,7 @@
 	.get_free_region   = generic_get_free_region,
 	.validate_add_page = amd_validate_add_page,
 	.have_wrcomb       = positive_have_wrcomb,
+	.num_var_ranges	   = common_num_var_ranges,
 };
 
 int __init amd_init_mtrr(void)

@@ -213,6 +213,7 @@
 	.get_free_region   = centaur_get_free_region,
 	.validate_add_page = centaur_validate_add_page,
 	.have_wrcomb       = positive_have_wrcomb,
+	.num_var_ranges	   = common_num_var_ranges,
 };
 
 int __init centaur_init_mtrr(void)

@@ -263,6 +263,7 @@
 	.get_free_region   = cyrix_get_free_region,
 	.validate_add_page = generic_validate_add_page,
 	.have_wrcomb       = positive_have_wrcomb,
+	.num_var_ranges	   = common_num_var_ranges,
 };
 
 int __init cyrix_init_mtrr(void)

@@ -667,4 +667,5 @@
 	.set               = generic_set_mtrr,
 	.validate_add_page = generic_validate_add_page,
 	.have_wrcomb       = generic_have_wrcomb,
+	.num_var_ranges	   = common_num_var_ranges,
 };

@@ -99,7 +99,7 @@
 }
 
 /*  This function returns the number of variable MTRRs  */
-static void __init set_num_var_ranges(void)
+int __init common_num_var_ranges(void)
 {
 	unsigned long config = 0, dummy;
 

@@ -109,7 +109,7 @@
 		config = 2;
 	else if (is_cpu(CYRIX) || is_cpu(CENTAUR))
 		config = 8;
-	num_var_ranges = config & 0xff;
+	return config & 0xff;
 }
 
 static void __init init_table(void)

@@ -1676,12 +1676,17 @@
 void __init mtrr_bp_init(void)
 {
 	u32 phys_addr;
+
 	init_ifs();
 
 	phys_addr = 32;
 
 	if (cpu_has_mtrr) {
 		mtrr_if = &generic_mtrr_ops;
+#ifdef CONFIG_XEN_DOM0
+		xen_init_mtrr();
+#endif
+
 		size_or_mask = 0xff000000;	/* 36 bits */
 		size_and_mask = 0x00f00000;
 		phys_addr = 36;

@@ -1739,7 +1744,7 @@
 	}
 
 	if (mtrr_if) {
-		set_num_var_ranges();
+		num_var_ranges = mtrr_if->num_var_ranges();
 		init_table();
 		if (use_intel()) {
 			get_mtrr_state();

@@ -50,6 +50,8 @@
 	int	(*validate_add_page)(unsigned long base, unsigned long size,
 				     unsigned int type);
 	int	(*have_wrcomb)(void);
+
+	int	(*num_var_ranges)(void);
 };
 
 extern int generic_get_free_region(unsigned long base, unsigned long size,

@@ -61,6 +63,8 @@
 
 extern int positive_have_wrcomb(void);
 
+extern int __init common_num_var_ranges(void);
+
 /* library functions for processor-specific routines */
 struct set_mtrr_context {
 	unsigned long flags;

@@ -104,3 +108,4 @@
 int amd_init_mtrr(void);
 int cyrix_init_mtrr(void);
 int centaur_init_mtrr(void);
+void xen_init_mtrr(void);

59 lines not on this page · raw message

@@ -6,9 +6,11 @@
 #ifdef CONFIG_X86_PAT
 extern int pat_enabled;
 extern void validate_pat_support(struct cpuinfo_x86 *c);
+extern void pat_disable(char *reason);
 #else
 static const int pat_enabled;
 static inline void validate_pat_support(struct cpuinfo_x86 *c) { }
+static inline void pat_disable(char *reason) { }
 #endif
 
 extern void pat_init(void);

@@ -17,6 +19,4 @@
 		unsigned long req_type, unsigned long *ret_type);
 extern int free_memtype(u64 start, u64 end);
 
-extern void pat_disable(char *reason);
-
 #endif /* _ASM_X86_PAT_H */

@@ -48,6 +48,7 @@
 #include <asm/pgtable.h>
 #include <asm/tlbflush.h>
 #include <asm/reboot.h>
+#include <asm/pat.h>
 
 #include "xen-ops.h"
 #include "mmu.h"

@@ -1743,6 +1744,8 @@
 		add_preferred_console("hvc", 0, NULL);
 	}
 
+	pat_disable("PAT disabled on Xen");
+
 	xen_raw_console_write("about to get started...\n");
 
 	/* Start the world */

@@ -112,13 +112,9 @@
  */
 static inline unsigned long mfn_to_local_pfn(unsigned long mfn)
 {
-	extern unsigned long max_mapnr;
 	unsigned long pfn = mfn_to_pfn(mfn);
-	if ((pfn < max_mapnr)
-	    && !xen_feature(XENFEAT_auto_translated_physmap)
-	    && (get_phys_to_machine(pfn) != mfn))
-		return max_mapnr; /* force !pfn_valid() */
-	/* XXX fixme; not true with sparsemem */
+	if (get_phys_to_machine(pfn) != mfn)
+		return -1; /* force !pfn_valid() */
 	return pfn;
 }
 

@@ -1162,11 +1162,19 @@
 #ifdef CONFIG_X86_LOCAL_APIC
 	case FIX_APIC_BASE:	/* maps dummy local APIC */
 #endif
+		/* All local page mappings */
 		pte = pfn_pte(phys, prot);
 		break;
 
+	case FIX_PARAVIRT_BOOTMAP:
+		/* This is an MFN, but it isn't an IO mapping from the
+		   IO domain */
+		pte = mfn_pte(phys, prot);
+		break;
+
 	default:
-		pte = mfn_pte(phys, prot);
+		/* By default, set_fixmap is used for hardware mappings */
+		pte = mfn_pte(phys, __pgprot(pgprot_val(prot) | _PAGE_IOMAP));
 		break;
 	}
 

@@ -1695,7 +1703,9 @@
 
 	/* Prevent unwanted bits from being set in PTEs. */
 	__supported_pte_mask &= ~_PAGE_GLOBAL;
-	if (!xen_initial_domain())
+	if (xen_initial_domain())
+		__supported_pte_mask |= _PAGE_IOMAP;
+	else
 		__supported_pte_mask &= ~(_PAGE_PWT | _PAGE_PCD);
 
 	/* Don't do the full vcpu_info placement stuff until we have a

98 lines not on this page · raw message

@@ -56,7 +56,14 @@
 typedef struct { pgdval_t pgd; } pgd_t;
 typedef struct { pgprotval_t pgprot; } pgprot_t;
 
-extern int page_is_ram(unsigned long pagenr);
+extern int native_page_is_ram(unsigned long pagenr);
+#ifndef CONFIG_PARAVIRT
+static inline int page_is_ram(unsigned long pagenr)
+{
+	return native_page_is_ram(pagenr);
+}
+#endif
+
 extern int pagerange_is_ram(unsigned long start, unsigned long end);
 extern int devmem_is_allowed(unsigned long pagenr);
 extern void map_devmem(unsigned long pfn, unsigned long size,

@@ -321,6 +321,8 @@
 	   an mfn.  We can tell which is which from the index. */
 	void (*set_fixmap)(unsigned /* enum fixed_addresses */ idx,
 			   unsigned long phys, pgprot_t flags);
+
+	int (*page_is_ram)(unsigned long pfn);
 };
 
 struct raw_spinlock;

@@ -1386,6 +1388,11 @@
 	pv_mmu_ops.set_fixmap(idx, phys, flags);
 }
 
+static inline int page_is_ram(unsigned long pfn)
+{
+	return PVOP_CALL1(int, pv_mmu_ops.page_is_ram, pfn);
+}
+
 void _paravirt_nop(void);
 #define paravirt_nop	((void *)_paravirt_nop)
 

@@ -451,6 +451,7 @@
 	},
 
 	.set_fixmap = native_set_fixmap,
+	.page_is_ram = native_page_is_ram,
 };
 
 EXPORT_SYMBOL_GPL(pv_time_ops);

@@ -97,7 +97,7 @@
 
 #endif
 
-int page_is_ram(unsigned long pagenr)
+int native_page_is_ram(unsigned long pagenr)
 {
 	resource_size_t addr, end;
 	int i;

@@ -1190,6 +1190,16 @@
 #endif
 }
 
+static int xen_page_is_ram(unsigned long pfn)
+{
+	/* Granted pages are not RAM.  They will not have a proper
+	   identity pfn<->mfn translation. */
+	if (mfn_to_local_pfn(pfn_to_mfn(pfn)) != pfn)
+		return 0;
+
+	return native_page_is_ram(pfn);
+}
+
 static const struct pv_info xen_info __initdata = {
 	.paravirt_enabled = 1,
 	.shared_kernel_pmd = 0,

@@ -1364,6 +1374,7 @@
 	},
 
 	.set_fixmap = xen_set_fixmap,
+	.page_is_ram = xen_page_is_ram,
 };
 
 static void xen_reboot(int reason)

@@ -1166,6 +1166,16 @@
 		pte = pfn_pte(phys, prot);
 		break;
 
+#ifdef CONFIG_X86_IO_APIC
+	case FIX_IO_APIC_BASE_0 ... FIX_IO_APIC_BASE_END:
+		/*
+		 * We just don't map the IO APIC - all access is via
+		 * hypercalls.  Keep the address in the pte for reference.
+		 */
+		pte = pfn_pte(phys, PAGE_NONE);
+		break;
+#endif
+
 	case FIX_PARAVIRT_BOOTMAP:
 		/* This is an MFN, but it isn't an IO mapping from the
 		   IO domain */

66 lines not on this page · raw message

@@ -1750,6 +1750,8 @@
 		set_iopl.iopl = 1;
 		if (HYPERVISOR_physdev_op(PHYSDEVOP_set_iopl, &set_iopl) == -1)
 			BUG();
+
+		xen_init_apic();
 	}
 
 	/* set the limit of our address space */

@@ -64,6 +64,8 @@
 #endif
 
 
+void xen_init_apic(void);
+
 /* Declare an asm function, along with symbols needed to make it
    inlineable */
 #define DECL_ASM(ret, name, ...)		\

Index: linux-2.6/arch/x86/xen/xen-ops.h
===================================================================
@@ -64,7 +64,11 @@ static inline void xen_smp_init(void) {}
 #endif
 
 
+#ifdef CONFIG_XEN_DOM0
 void xen_init_apic(void);
+#else
+static inline void xen_init_apic(void) { ; }
+#endif
 
 /* Declare an asm function, along with symbols needed to make it
    inlineable */

@@ -806,8 +806,11 @@
 
 static struct irq_chip xen_dynamic_chip __read_mostly = {
 	.name		= "xen-dyn",
+
+	.disable	= disable_dynirq,
 	.mask		= disable_dynirq,
 	.unmask		= enable_dynirq,
+
 	.ack		= ack_dynirq,
 	.set_affinity	= set_affinity_irq,
 	.retrigger	= retrigger_dynirq,

@@ -15,10 +15,4 @@
 	return raw_irqs_disabled_flags(regs->flags);
 }
 
-static inline void xen_do_IRQ(int irq, struct pt_regs *regs)
-{
-	regs->orig_ax = ~irq;
-	do_IRQ(regs);
-}
-
 #endif /* _ASM_X86_XEN_EVENTS_H */

@@ -19,21 +19,6 @@
 	(void)HYPERVISOR_xen_version(0, NULL);
 }
 
-static void __init __xen_init_IRQ(void)
-{
-	int i;
-
-	/* Create identity vector->irq map */
-	for(i = 0; i < NR_VECTORS; i++) {
-		int cpu;
-
-		for_each_possible_cpu(cpu)
-			per_cpu(vector_irq, cpu)[i] = i;
-	}
-
-	xen_init_IRQ();
-}
-
 static unsigned long xen_save_fl(void)
 {
 	struct vcpu_info *vcpu;

@@ -123,7 +108,7 @@
 }
 
 static const struct pv_irq_ops xen_irq_ops __initdata = {
-	.init_IRQ = __xen_init_IRQ,
+	.init_IRQ = xen_init_IRQ,
 	.save_fl = xen_save_fl,
 	.restore_fl = xen_restore_fl,
 	.irq_disable = xen_irq_disable,

@@ -29,6 +29,7 @@
 
 #include <asm/ptrace.h>
 #include <asm/irq.h>
+#include <asm/idle.h>
 #include <asm/sync_bitops.h>
 #include <asm/xen/hypercall.h>
 #include <asm/xen/hypervisor.h>

@@ -503,6 +504,24 @@
 }
 
 
+static void xen_do_irq(unsigned irq, struct pt_regs *regs)
+{
+	struct pt_regs *old_regs = set_irq_regs(regs);
+
+	if (WARN_ON(irq == -1))
+		return;
+
+	exit_idle();
+	irq_enter();
+
+	//printk("cpu %d handling irq %d\n", smp_processor_id(), info->irq);
+	handle_irq(irq, regs);
+
+	irq_exit();
+
+	set_irq_regs(old_regs);
+}
+
 /*
  * Search the CPUs pending events bitmasks.  For each one found, map
  * the event number to an irq, and feed it into do_IRQ() for

@@ -543,8 +562,7 @@
 				int port = (word_idx * BITS_PER_LONG) + bit_idx;
 				int irq = evtchn_to_irq[port];
 
-				if (irq != -1)
-					xen_do_IRQ(irq, regs);
+				xen_do_irq(irq, regs);
 			}
 		}
 

@@ -51,18 +51,8 @@
 /* IRQ <-> IPI mapping */
 static DEFINE_PER_CPU(int, ipi_to_irq[XEN_NR_IPIS]) = {[0 ... XEN_NR_IPIS-1] = -1};
 
-/* Packed IRQ information: binding type, sub-type index, and event channel. */
-struct packed_irq
-{
-	unsigned short evtchn;
-	unsigned char index;
-	unsigned char type;
-};
-
-static struct packed_irq irq_info[NR_IRQS];
-
-/* Binding types. */
-enum {
+/* Interrupt types. */
+enum xen_irq_type {
 	IRQT_UNBOUND,
 	IRQT_PIRQ,
 	IRQT_VIRQ,